{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:L4AG4CKL4LPVI2TDXB3L6GK4NK","short_pith_number":"pith:L4AG4CKL","schema_version":"1.0","canonical_sha256":"5f006e094be2df546a63b876bf195c6a95945169f7d6d21dee29cba2d660038c","source":{"kind":"arxiv","id":"2005.03557","version":2},"attestation_state":"computed","paper":{"title":"Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Tengyu Xu, Yingbin Liang, Zhe Wang","submitted_at":"2020-05-07T15:42:31Z","abstract_excerpt":"As an important type of reinforcement learning algorithms, actor-critic (AC) and natural actor-critic (NAC) algorithms are often executed in two ways for finding optimal policies. In the first nested-loop design, actor's one update of policy is followed by an entire loop of critic's updates of the value function, and the finite-sample analysis of such AC and NAC algorithms have been recently well established. The second two time-scale design, in which actor and critic update simultaneously but with different learning rates, has much fewer tuning parameters than the nested-loop design and is he"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2005.03557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T15:42:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"15f4283f5e2e0ee0d88d343185085d04e4a6c0def1ce49ea284094fd14687c5f","abstract_canon_sha256":"942db39dde827a9c4ed96c707c7b7f8b8fb989f68d13935e93bd93fc1d373a76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:25.095364Z","signature_b64":"OElURGLtUnno3LUpaI9kWV9aedpd8Gxa1eO3Y4C2XWHGE9eFNDS5bg3ED1fi3tLilLbPxBkdKEFy29hq7y9rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f006e094be2df546a63b876bf195c6a95945169f7d6d21dee29cba2d660038c","last_reissued_at":"2026-07-05T01:01:25.095013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:25.095013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Tengyu Xu, Yingbin Liang, Zhe Wang","submitted_at":"2020-05-07T15:42:31Z","abstract_excerpt":"As an important type of reinforcement learning algorithms, actor-critic (AC) and natural actor-critic (NAC) algorithms are often executed in two ways for finding optimal policies. In the first nested-loop design, actor's one update of policy is followed by an entire loop of critic's updates of the value function, and the finite-sample analysis of such AC and NAC algorithms have been recently well established. The second two time-scale design, in which actor and critic update simultaneously but with different learning rates, has much fewer tuning parameters than the nested-loop design and is he"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03557","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.03557/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2005.03557","created_at":"2026-07-05T01:01:25.095070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.03557v2","created_at":"2026-07-05T01:01:25.095070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03557","created_at":"2026-07-05T01:01:25.095070+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4AG4CKL4LPV","created_at":"2026-07-05T01:01:25.095070+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4AG4CKL4LPVI2TD","created_at":"2026-07-05T01:01:25.095070+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4AG4CKL","created_at":"2026-07-05T01:01:25.095070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22579","citing_title":"Stationary Robust Mean-Field Games under Model Mismatches","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03893","citing_title":"Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01505","citing_title":"Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13639","citing_title":"Achieving $\\epsilon^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK","json":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK.json","graph_json":"https://pith.science/api/pith-number/L4AG4CKL4LPVI2TDXB3L6GK4NK/graph.json","events_json":"https://pith.science/api/pith-number/L4AG4CKL4LPVI2TDXB3L6GK4NK/events.json","paper":"https://pith.science/paper/L4AG4CKL"},"agent_actions":{"view_html":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK","download_json":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK.json","view_paper":"https://pith.science/paper/L4AG4CKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.03557&json=true","fetch_graph":"https://pith.science/api/pith-number/L4AG4CKL4LPVI2TDXB3L6GK4NK/graph.json","fetch_events":"https://pith.science/api/pith-number/L4AG4CKL4LPVI2TDXB3L6GK4NK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/action/storage_attestation","attest_author":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/action/author_attestation","sign_citation":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/action/citation_signature","submit_replication":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/action/replication_record"}},"created_at":"2026-07-05T01:01:25.095070+00:00","updated_at":"2026-07-05T01:01:25.095070+00:00"}